WO2014071718A1

WO2014071718A1 - Topology grading method and apparatus, and flooding processing method and apparatus

Info

Publication number: WO2014071718A1
Application number: PCT/CN2013/073481
Authority: WO
Inventors: 李建飞; 王戎
Original assignee: 华为技术有限公司
Priority date: 2012-11-08
Filing date: 2013-03-29
Publication date: 2014-05-15
Also published as: US20150195201A1; US9722924B2; EP2863595A1; CN103812779B; EP2863595B1; EP2863595A4; CN103812779A

Abstract

Embodiments of the present invention disclose a topology grading method and apparatus, and a flooding processing method and apparatus. The method comprises: firstly, a controller receiving a data packet reported by a switch connected to a source host; then, the controller retrieving in a local device physical address (MAC address) list to determine whether a destination address of the data packet exists; if the destination address of the data packet does not exist, the controller obtaining a destination port, the destination port being a port of a switch connected to a destination host and the destination host is another host different from the source host, and finally, the controller generating a routing table by using the destination port as the destination address, and sending the routing table to the switch connected to the source host, so that the switch connected to the source host forwards the data packet according to the routing table. The present invention is applicable to the field of a communications system.

Description

Topological classification method, device and flooding processing method and device

This application is submitted to the Chinese Patent Office on November 08, 2012, and the application number is

201210444069.4, the entire disclosure of which is hereby incorporated by reference in its entirety in its entirety in its entirety in the the the the the the the the the the

Technical field

The present invention relates to the field of communication systems, and in particular, to a topology grading method, apparatus, and flood processing method and apparatus.

Background technique

In a traditional computer network, each switch can only obtain information about neighboring switches, and there is no global network view for each switch. A network based on SDN (Software Defined Network) technology is one of the important trends in the future development of the network. The core idea of SDN is to separate the network device control plane from the data forwarding plane. The switch is strictly based on the forwarding table forwarding; the switch provides an interface API (Application Programming Interface) for controller control; the switch and the controller follow a certain protocol.

In the SDN network, the initial routing table of the switch is empty. When the received data packet cannot find a matching routing table in the switch, it reports to the controller to request a forwarding policy. If the controller can find the destination address in the MAC address table of the local device, the switch selects a path for the switch and sends the corresponding routing table to the switch. If the reported packet cannot find its destination address in the local MAC table, the controller instructs the switch to flood the port of all other switches in the network except the receiving port. However, this can result in repeated broadcasts of packets in the network, causing broadcast storms.

Summary of the invention

The embodiments of the present invention provide a topology grading method, a device, and a flooding processing method and device, which can hierarchically distinguish switches in a network, and effectively suppress flooding and eliminate The repeated broadcast of the data packet in the network increases the availability of the link.

The technical solution adopted by the embodiment of the present invention is:

A topology grading method, including:

The controller acquires a switch connected to the host according to the topology information of the switch in the network; the controller configures the switch connected to the host as a layer 1 switch;

The controller acquires an unlayered switch in the network, and configures, in the unlayered switch, a switch directly connected to the layer N switch as an N+1 switch, where N is the number of layers in which the switch is located. , the N is a positive integer.

The controller acquires a switch connected to the host according to the topology information of the switch in the network, including:

The controller obtains a port that is opened by the switch according to the topology information of the switch in the network; and the controller determines whether a port connected to the host exists in the port opened by the switch;

If there is a port connected to the host in the port opened by the switch, the controller confirms that the switch is the switch connected to the host.

The controller acquires a switch that is not layered in the network, and configures the switch that is directly connected to the layer N switch in the unlayered switch to be an N+1 layer switch, and further includes: when the controller receives When the data packet is reported by the switch connected to the source host, the controller searches whether the destination address of the data packet exists in the local device physical address MAC address table;

If the destination address of the data packet does not exist, the controller acquires a destination port, where the destination port is a port of a switch connected to the target host, and the target host is a host other than the source host;

The controller uses the destination port as a destination address, generates a routing table, and sends the routing table to the switch connected to the source host, so that the switch connected to the source host forwards according to the routing table. The data packet. If the destination address of the data packet does not exist, the controller acquiring the destination port includes: the controller acquiring, according to the topology classification, the port opened by the switch connected to the target host, not connected to another switch The port acts as the destination port.

A flooding approach, including:

The controller receives the data packet reported by the switch connected to the source host;

Determining, by the controller, a destination address of the data packet in a local device physical address MAC address table;

The controller uses the destination port as a destination address, generates a routing table, and sends the routing table to the switch connected to the source host, so that the switch connected to the source host forwards according to the routing table. The data packet.

If the destination address of the data packet does not exist, the controller acquiring the destination port includes: the controller performs topology classification on the switch in the network;

The controller obtains, according to the topology classification, a port that is not connected to another switch in the port opened by the switch connected to the target host as the destination port.

The data packet is an Address Resolution Protocol APR request, and/or an unknown unicast frame, and/or a Dynamic Host Configuration Protocol DHCP data.

When the data packet is an address resolution protocol APR request, if the destination address of the data packet does not exist, the controller further includes:

The controller selects a port whose host information is unknown from the destination port, and uses the port whose connection host information is unknown as the destination address.

If the destination address of the APR request exists in the local MAC address table, the controller Directly replying to the APR request sent by the source host.

A topology grading device comprising:

a first acquiring unit, configured to acquire a switch connected to the host according to the topology information of the switch in the network;

a configuration unit, configured to configure, by the first acquiring unit, a switch connected to the host as a layer 1 switch;

The first obtaining unit is further configured to acquire a switch that is not layered in the network;

The configuration unit is further configured to configure, in the un-layered switch acquired by the first acquiring unit, a switch directly connected to the layer N switch as an N+1 layer switch, where the N is a layer where the switch is located. , the N is a positive integer.

The obtaining unit includes:

An obtaining module, configured to obtain, according to the topology information of the switch in the network, a port that is opened by the switch;

a judging module, configured to determine whether a port connected to the host exists in the port opened by the switch acquired by the acquiring module;

And a confirmation module, configured to: if the determining module determines that a port connected to the host exists in the port opened by the switch, confirm that the switch is the switch connected to the host.

The device also includes:

a retrieval unit, configured to: when receiving a data packet reported by the switch connected to the source host, searching for a destination address of the data packet in a local device physical address MAC address table; The retrieval unit retrieves a destination address of the data packet, and acquires a destination port, where the destination port is a port of a switch connected to the target host, and the target host is a host other than the source host;

a generating unit, configured to use the destination port obtained by the second acquiring unit as a destination address, generate a routing table, and send the routing table to the switch connected to the source host, so that the source host is connected The switch forwards the data packet according to the routing table. The second obtaining unit is configured to obtain, according to the topology classification, a port that is not connected to another switch, and the port that is connected to the switch connected to the target host, as the destination port.

A flooding processing device, comprising:

a receiving unit, configured to receive a data packet reported by a switch connected to the source host;

a retrieval unit, configured to retrieve, in a local device physical address MAC address table, whether there is a destination address of the data packet received by the receiving unit; after the address, obtain a destination port, where the destination port is a port of a switch connected to the target host The target host is a different host than the source host;

a sending unit, configured to use the destination port obtained by the acquiring unit as a destination address, generate a routing table, and send the routing table to the switch connected to the source host and the switch that needs to forward the data packet, so that The switch connected to the source host and the switch that needs to forward the data packet forward the data packet according to the routing table.

The obtaining unit includes:

a grading module, configured to perform topology grading on switches in the network;

And an obtaining module, configured to obtain, according to the topology classification performed by the grading module, a port that is not connected to another switch, and a port that is connected to the switch connected to the target host, as the destination port.

The device also includes:

And a selecting unit, configured to select, from the destination port acquired by the acquiring unit, a port whose host information is not connected, and use the port whose connection host information is unknown as the destination address.

a reply unit, configured to directly reply to the APR request sent by the source host received by the receiving unit if the destination address of the APR request exists in the local MAC address table. The topology grading method, device, and flood processing method and device provided by the embodiment of the present invention firstly, the controller receives a data packet reported by a switch connected to the source host; and then the controller locally addresses the device physical address MAC address table. Retrieving whether there is a destination address of the data packet. If the destination address of the data packet does not exist, the controller acquires a destination port, where the destination port is a port of a switch connected to the target host, and the target host is Different from the host other than the source host; finally, the controller uses the destination port as a destination address, and sends the routing table to the switch connected to the source host, so that the source host is connected The switch forwards the data packet according to the routing table. In an SDN network, if the data packet reported by the switch cannot find its destination address in the local MAC table, the controller usually instructs the switch to flood the port of all other switches in the network except the receiving port. Go out. However, this can result in repeated broadcasts of data packets in the network, causing broadcast storms. In the embodiment of the present invention, the switch performs topology classification on the switch in the network. When the data packet reported by the switch cannot find the destination address in the local MAC address table, the routing table is configured for the switch, so that the switch forwards the data packet only. The port of the switch connected to the target host obtained by the controller according to the topology classification effectively suppresses flooding, eliminates repeated broadcast of the data packet in the network, and increases the availability of the link.

DRAWINGS

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the embodiments or the description of the prior art will be briefly described below. Obviously, the drawings in the following description are merely the present invention. Some of the embodiments may be obtained by those of ordinary skill in the art in view of these drawings without any inventive effort.

FIG. 1 is a flowchart of a topology grading method according to an embodiment of the present invention;

2 is a schematic structural diagram of a topology grading device according to an embodiment of the present invention;

FIG. 3 is a flowchart of a flooding processing method according to an embodiment of the present invention;

4 is a schematic structural diagram of a flooding processing apparatus according to an embodiment of the present invention; FIG. 5 is a schematic structural diagram of a controller according to an embodiment of the present invention; FIG. 6 is a schematic diagram of a topology of a switch in a network according to an embodiment of the present invention; FIG. 7 is a schematic diagram of a topology of a switch in a network according to an embodiment of the present invention;

FIG. 8 is a schematic diagram of a state of a switch port according to an embodiment of the present invention.

detailed description

The technical solutions in the embodiments of the present invention are clearly and completely described in conjunction with the drawings in the embodiments of the present invention. It is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present invention without creative efforts are within the scope of the present invention.

In order to make the advantages of the technical solutions of the present invention clearer, the present invention will be described in detail below with reference to the accompanying drawings and embodiments.

This embodiment provides a topology grading method. As shown in FIG. 1, the method includes:

101. The controller acquires a switch connected to the host according to the topology information of the switch in the network.

Specifically, the controller acquires a port that is opened by the switch according to the topology information of the switch in the network; the controller determines whether a port connected to the host exists in the port opened by the switch; There is a port connected to the host, and the controller confirms that the switch is the switch connected to the host.

For example, the port opened by the switch in Figure 8 has ports Por t 1, Por t 2, Por t 3, Por t 4, Por t 5 , where Por tl, Por t 2, Por t 3 are connected to other switches, then control It is possible to determine that the switch's Por t 4 and Por t 5 are the ports connected to the host.

102. The controller configures the switch connected to the host to be a layer 1 switch.

103. The controller acquires an unlayered switch in the network, and configures, in the unlayered switch, a switch directly connected to the layer N switch as an Nth layer switch.

Where N is the number of layers in which the switch is located, and the N is a positive integer.

Specifically, the controller configures the switch that contains the host port as the layer 1 switch. Same In the example, in the unlayered switch, the controller is directly connected to the switch of the layer 1 switch as the layer 2 switch; and so on, in the unlayered switch, the N is directly connected to the N-1 layer switch. Layer switch. According to this rule, all switches in the network can be classified.

For the topology grading method provided in this embodiment, the specific data structure may be as follows: <key, value> = (layer i, value), i = l, 2, ... N. The shell's Layer 1 switch is stored as: Key=layer 1; Va lue=<Sw ID, Ports to hosts, last seen Time>; The Layer 2 switch directly connected to the Layer 1 switch is stored as: Key= Layer2; Value= <Sw ID, Links to layerl, last seen Time>. The Nth layer switch connected to the (N_1)th layer switch is stored as: Key=layer N; Value= <SwID, Links to layer (N-1) , last seen Time>. And so on, until all the exchanges are categorized. Updating the data structure of the layer 1 switch when the addition/deletion of the host in the network, and/or the addition or deletion of the switch, and/or the addition/deletion of the link cause a change in the location of the switch; updating the connection to the switch The location of other switches; and so on, until all switches are updated.

Further, after the step 103, the method may further include: when the controller receives the data packet reported by the switch connected to the source host, the controller searches whether the data packet exists in the local device physical address MAC address table. If the destination address of the data packet does not exist, the controller obtains the destination port according to the topology, and the destination port is a port of the switch connected to the target host, where the target host is different from the a host other than the source host; the controller uses the destination port as a destination address, generates a routing table, and sends the routing table to the switch connected to the source host, so that the source host is connected The switch forwards the data packet according to the routing table.

The topology of the switch in the network provided in this embodiment can be as shown in FIG. 7, and the topology of the switch in the existing network can be as shown in FIG. 8. It can be seen from the figure that the existing topology is in the network. The switch in the present embodiment does not have any distinction, and the topology grading method provided in this embodiment can layer the switches in the network, that is, the switches in the network can be distinguished hierarchically, so that the controller can control the switch to have a destination. Forwarding packets, effectively suppressing flooding, Eliminates the repeated broadcast of packets in the network, increasing the availability of the link.

The present embodiment provides a topology grading device. As shown in FIG. 2, the entity of the device may be a controller, and the device may include: a first acquiring unit 21 and a configuration unit 22.

The first obtaining unit 21 may be configured to obtain a switch connected to the host according to the topology information of the switch in the network.

The first obtaining unit 21 may specifically include:

The obtaining module 2101 is configured to obtain, according to the topology information of the switch in the network, a port that is opened by the switch.

The determining module 2102 is configured to determine whether a port connected to the host exists in the port opened by the switch acquired by the obtaining module 2101.

The confirmation module 2103 may be configured to: if the determining module 2102 determines that a port connected to the host exists in the port opened by the switch, confirm that the switch is the switch connected to the host.

The configuration unit 22 is configured to configure the switch connected to the host acquired by the first obtaining unit 21 to be a layer 1 switch.

The first obtaining unit 21 can also be used to acquire an unlayered switch in the network.

The configuration unit 22 is further configured to configure, in the unlayered switch acquired by the first acquiring unit 21, a switch directly connected to the layer N switch as an N+1th layer switch, where the N is a switch The number of layers, the N being a positive integer.

Further, the device may further include:

The retrieving unit 23 can be configured to retrieve, in the local device physical address MAC address table, whether the destination address of the data packet exists when receiving the data packet reported by the switch connected to the source host.

The second obtaining unit 24 may be configured to: if the searching unit 23 retrieves a destination address where the data packet does not exist, obtain a destination port, where the destination port is a port of a switch connected to the target host, where the target host is Different from other hosts outside the source host. The second obtaining unit 24 is specifically configured to obtain, according to the topology classification, a port that is not connected to another switch, and the port that is connected to the switch connected to the target host, as the destination port.

The generating unit 25 may be configured to use the destination port obtained by the second obtaining unit 24 as a destination address, generate a routing table, and send the routing table to the switch connected to the source host, so that the source and the source The switch connected by the host forwards the data packet according to the routing table.

It should be noted that, for the corresponding descriptions of the functional units involved in the topology grading apparatus provided in this embodiment, reference may be made to the corresponding description in FIG. 1 , and details are not described herein again.

The topology grading device provided in this embodiment can hierarchically switch the switches in the network by hierarchically arranging the switches in the network, so that the controller can control the switch to forward the data packets in a targeted manner, thereby effectively suppressing. Flooding eliminates duplicate broadcasts of packets in the network, increasing the availability of links.

This embodiment provides a flooding processing method. As shown in FIG. 3, the method includes: 301. A controller receives a data packet reported by a switch connected to a source host.

The data packet is an address resolution protocol APR request, and/or an unknown unicast frame, and/or a dynamic host configuration protocol DHCP data. The rules for classifying switches in this embodiment are based on the topology ranking method provided in FIG.

302. The controller searches, in the local device physical address MAC address table, whether the destination address of the data packet exists.

Optionally, if the destination address of the data packet exists, the data packet is forwarded according to the destination address.

303. If the destination address of the data packet does not exist, the controller acquires a destination port. The destination port is a port of a switch connected to the target host, and the target host is a host other than the source host, and the target host may be one or more.

Specifically, the controller performs topology classification on the switch in the network, and then obtains, according to the topology classification, the port opened by the switch connected to the target host, not The port to which his switch is connected serves as the destination port.

Optionally, when the data packet is an address resolution protocol (APR) request, the step 303 may further include: if the destination address of the APR request exists in the local MAC address table, the controller directly replies to the source host The APR request sent. After the step 303, the method further includes: selecting, from the destination port, a port whose host information is unknown, and using the port whose host information is unknown as the destination address, so as to effectively converge the ARP unicast data packet, thereby reducing Unnecessary data packets in the network.

For example, first host lpi ng (executable command) host 9, at this time through the controller decision, the ARP request sent by host 1 will be unicast to host 4, host 6, host 9; then host lpi ng host 6, at this time The controller decides that the ARP request sent by the host 1 will be unicast to the host 4, the host 6; then the host 1 pi ng the host 4, then the ARP request sent by the host 1 is only unicast to the host 4, so that it can effectively converge ARP unicast packets reduce unnecessary packets on the network. After that, since the controller already knows the information of all the hosts, when there is another p i ng, the controller can directly reply to the ARP request. Specifically, the controller sends the MAC address of the destination host to the host that initiated the request.

304. The controller uses the destination port as a destination address, generates a routing table, and sends the routing table to the switch connected to the source host.

Further, the switch that is connected to the source host forwards the data packet according to the routing table.

The method provided in this embodiment is to perform topology classification on the switch in the network by the controller. When the data packet reported by the switch cannot find the destination address in the local MAC address table, configure a routing table for the switch, so that the switch will The data packet is only forwarded to the port of the switch connected to the target host, which effectively suppresses flooding, eliminates duplicate broadcast of data packets in the network, and increases the availability of the link.

The embodiment provides a flooding processing device. As shown in FIG. 4, the device may include: a receiving unit 41, a retrieving unit 42, an obtaining unit 43, and a sending unit 44. The receiving unit 41 is configured to receive a data packet reported by the switch connected to the source host. The data packet is an address resolution protocol APR request, and/or an unknown unicast frame, and/or a dynamic host configuration protocol DHCP data.

The retrieval unit 42 can be configured to retrieve, in the local device physical address MAC address table, whether the destination address of the data packet received by the receiving unit 41 exists.

The obtaining unit 43 may be used by the searching unit 42 to retrieve the destination address of the data packet in the MAC table, and obtain the destination port.

The destination port is a port of a switch connected to the target host, and the target host is a host other than the source host.

The obtaining unit 43 may specifically include:

The grading module 4301 can be used to perform topology grading on switches in the network.

The obtaining module 4302 may be configured to obtain, according to the topology classification performed by the grading module, a port that is not connected to another switch, and a port that is not connected to the switch, which is connected to the target host, is used as the destination port.

The sending unit 44 may be configured to use the destination port obtained by the obtaining unit 43 as a destination address, generate a routing table, and send the routing table to the switch connected to the source host.

The device may further include:

The selecting unit 45 is configured to select, from the destination port acquired by the obtaining unit 43, a port whose connection with the host information is unknown, and use the port whose connection host information is unknown as the destination address.

The replying unit 46 is configured to directly reply to the APR request sent by the source host received by the receiving unit 41 if the destination address of the APR request exists in the local MAC address table.

The entity of the flooding processing device provided in this embodiment may be a controller, and the controller may be deployed on a server device, including but not limited to a server device. As shown in FIG. 5, the controller includes: Receiver 51, processor 52, and transmitter 53.

The receiver 51 can be configured to receive a data packet reported by a switch connected to the source host.

The processor 52 can be configured to retrieve, in the local device physical address MAC address table, whether the destination address of the data packet received by the receiver 51 exists.

The processor 52 is further configured to obtain a destination port after the destination address of the data packet does not exist in the MAC table, where the destination port is a port of a switch connected to the target host, where the target host is different from the source Other hosts outside the host.

a transmitter 5 3, configured to use the destination port obtained by the processor 52 as a destination address, generate a routing table, and send the routing table to the switch connected to the source host, so that the source host is connected The switch forwards the data packet according to the routing table.

The processor 52 is specifically configured to perform topology grading on the switch in the network, and then obtain, according to the topology grading performed by the grading module, the port opened by the switch connected to the target host, and not connected to another switch. The connected port acts as the destination port.

The processor 52 may be further configured to select, from the destination port, a port whose connection with the host information is unknown, and use the port whose connection host information is unknown as the destination address.

The processor 52 may be further configured to directly reply to the APR request sent by the source host received by the receiver 31 if the destination address of the APR request exists in the local MAC address table.

It should be noted that other corresponding descriptions of the various functional units involved in the flooding processing apparatus and the controller provided in this embodiment may refer to the corresponding description in FIG. 3, which will not be further described herein.

The device provided in this embodiment performs topology classification on the switch in the network by the controller. When the data packet reported by the switch cannot find the destination address in the local MAC address table, the routing table is configured for the switch, so that the switch will The data packet is only forwarded to the port of the switch connected to the target host, which effectively suppresses flooding, eliminates duplicate broadcast of data packets in the network, and increases the availability of the link.

The topology grading device and the flooding processing device provided by the embodiments of the present invention can implement the above For the implementation of the method, refer to the description in the method embodiment, and details are not described herein again. The topology grading method, apparatus, and flood processing method and apparatus provided by the embodiments of the present invention may be applied to the field of communication systems, but are not limited thereto.

A person skilled in the art can understand that all or part of the process of implementing the above embodiment method can be completed by a computer program to instruct related hardware, and the program can be stored in a computer readable storage medium. In execution, the flow of an embodiment of the methods as described above may be included. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

The above is only the specific embodiment of the present invention, but the scope of the present invention is not limited thereto, and any change or replacement that can be easily conceived by those skilled in the art within the technical scope of the present invention is All should be covered by the scope of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

claims

1. A flood treatment method, characterized by including:

The controller receives data packets reported by the switch connected to the source host;

The controller searches the local device physical address MAC address table to see whether the destination address of the data packet exists;

If the destination address of the data packet does not exist, the controller obtains the destination port. The destination port is the port of the switch connected to the target host, and the target host is a host other than the source host;

The controller uses the destination port as the destination address, generates a routing table, and sends the routing table to the switch connected to the source host, so that the switch connected to the source host forwards according to the routing table the data packet.

2. The flooding processing method according to claim 1, characterized in that, if the destination address of the data packet does not exist, the controller obtaining the destination port includes:

The controller performs topology classification on the switches in the network;

According to the topology classification, the controller obtains, among the ports opened by the switch connected to the target host, the ports that are not connected to other switches as the destination port.

3. The flooding processing method according to claim 1 or 2, characterized in that the data packet is an Address Resolution Protocol APR request, and/or an unknown unicast frame, and/or a Dynamic Host Configuration Protocol DHCP data.

4. The flooding processing method according to any one of claims 1 to 3, characterized in that when the data packet is an address resolution protocol APR request, if the destination address of the data packet does not exist, the After the controller obtains the destination port, it also includes:

The controller selects a port whose connected host information is unknown from the destination port, and uses the connected port whose host information is unknown as a destination address.

5. The flooding processing method according to any one of claims 1 to 4, characterized in that when the data packet is an address resolution protocol APR request, if the destination address of the data packet does not exist, Before the controller obtains the destination port, it also includes:

If the destination address of the APR request exists in the local MAC address table, the controller directly replies to the APR request sent by the source host.

6. A topological classification method, characterized by including:

The controller obtains the switch connected to the host according to the topology information of the switch in the network; the controller configures the switch connected to the host to be a layer 1 switch;

The controller obtains the unstratified switches in the network, and configures the switch directly connected to the Nth layer switch among the unlayered switches as the N+1th layer switch, where N is the number of layers where the switch is located. , the N is a positive integer.

7. The topology classification method according to claim 6, characterized in that, according to the topology information of the switches in the network, the controller obtains the switches connected to the host including:

The controller obtains the ports opened by the switch based on the topology information of the switch in the network;

The controller determines whether there is a port connected to the host among the ports opened by the switch;

If there is a port connected to the host among the ports opened by the switch, the controller confirms that the switch is the switch connected to the host.

8. The topology classification method according to claim 6, characterized in that the controller obtains the unlayered switches in the network and selects the switches directly connected to the Nth layer switch among the unlayered switches. After the switch is configured as an N+1 layer switch, it also includes:

When the controller receives the data packet reported by the switch connected to the source host, the controller searches the local device physical address MAC address table to see whether the destination address of the data packet exists;

If the destination address of the data packet does not exist, the controller obtains the destination port, where the destination port is a port of the switch connected to the target host, and the target host is a host other than the source host; The controller uses the destination port as the destination address, generates a routing table, and sends the routing table to the switch connected to the source host, so that the switch connected to the source host forwards according to the routing table the data packet.

9. The topology classification method according to claim 8, wherein if the destination address of the data packet does not exist, the controller obtaining the destination port includes:

According to the topology classification, the controller obtains the ports opened by the switch connected to the target host and the ports that are not connected to other switches as the destination ports.

10. A flood treatment device, characterized by including:

The receiving unit is used to receive data packets reported by the switch connected to the source host;

A retrieval unit, used to search in the local device physical address MAC address table whether there is a destination address of the data packet received by the receiving unit;

The acquisition unit is used to obtain the destination port after the retrieval unit retrieves the destination address of the data packet that does not exist in the MAC table. The destination port is the port of the switch connected to the target host. The target host is different from the destination address. Hosts other than the source host;

A sending unit, configured to use the destination port obtained by the acquisition unit as the destination address, generate a routing table, and send the routing table to the switch connected to the source host, so that the switch connected to the source host can The routing table forwards the data packet.

11. The flood processing device according to claim 10, characterized in that the acquisition unit includes:

Classification module, used for topological classification of switches in the network;

The acquisition module is configured to obtain, among the ports opened by the switch connected to the target host, the ports that are not connected to other switches as the destination ports according to the topology classification performed by the classification module.

12. The flooding processing device according to claim 10 or 11, characterized in that the data packet is an address resolution protocol APR request, and/or an unknown unicast frame, and/or a dynamic host configuration protocol DHCP data.

13. The flooding processing device according to any one of claims 10 to 12, characterized in that, when the data packet is an APR request, the device further includes:

A selection unit, configured to select a port for which the connected host information is unknown from the destination ports obtained by the acquisition unit, and use the connected port for which the host information is unknown as the destination address.

14. The flooding processing device according to any one of claims 10-13, characterized in that, when the data packet is an APR request, the device further includes:

A reply unit, configured to directly reply to the APR request sent by the source host received by the receiving unit if the destination address of the APR request exists in the local MAC address table.

15. A topology classification device, characterized in that it includes:

The first acquisition unit is used to acquire the switch connected to the host based on the topology information of the switch in the network;

A configuration unit configured to configure the switch connected to the host obtained by the first acquisition unit to be a layer 1 switch;

The first acquisition unit is also used to acquire unlayered switches in the network;

The configuration unit is also used to configure the switch directly connected to the Nth layer switch among the unlayered switches obtained by the first acquisition unit as the N+1th layer switch, where N is the layer where the switch is located. Number, the N is a positive integer.

16. The topology classification device according to claim 15, characterized in that the first acquisition unit includes:

The acquisition module is used to obtain the ports opened by the switch based on the topology information of the switch in the network;

A judgment module, used to judge whether there is a port connected to the host among the ports opened by the switch obtained by the acquisition module;

A confirmation module, configured to confirm that the switch is the switch connected to the host if the judgment module determines that among the ports opened by the switch, there is a port connected to the host.

17. The topology classification device according to claim 15, characterized in that, the device further include:

The retrieval unit is configured to, when receiving the data packet reported by the switch connected to the source host, search whether the destination address of the data packet exists in the local device physical address MAC address table; the second acquisition unit is used to search if the destination address of the data packet exists. The retrieval unit retrieves the destination address of the data packet that does not exist, and obtains the destination port. The destination port is a port of the switch connected to the target host, and the target host is a host other than the source host;

A generating unit, configured to use the destination port obtained by the second obtaining unit as the destination address, generate a routing table, and send the routing table to the switch connected to the source host, so that the switch connected to the source host The switch forwards the data packet according to the routing table.

18. The topology classification device according to claim 17, characterized in that the second acquisition unit is specifically configured to obtain the ports opened by the switch connected to the target host according to the topology classification. , the port that is not connected to other switches is used as the destination port.